Machine Learning Applications in Pest Identification for Chili Plants A Systematic Literature Review

Machine learning has rapidly emerged as a transformative tool in various sectors, including agriculture, where it has the potential to revolutionize pest management. This study investigates the application of machine learning algorithms in identifying pest types on chili plants, aiming to enhance agricultural productivity by reducing the negative impact of pest infestations. A Systematic Literature Review (SLR) was conducted, drawing on reputable databases such as Scopus, Elsevier, Google Scholar, Sinta, ACM Digital Library, ProQuest, and IEEE Xplore. The review evaluates and compares the performance of various machine learning models, with a particular focus on their accuracy and efficiency in pest type identification within an agricultural context. Key findings reveal that machine learning algorithms, particularly Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs), demonstrate promising results in pest identification, offering higher precision and faster processing times compared to traditional methods. However, challenges such as data quality, model generalization, and computational cost remain. The study provides valuable insights for researchers and practitioners, suggesting that the integration of machine learning in pest management can significantly improve the quality and productivity of chili farming. This work contributes to the growing body of knowledge on precision agriculture and highlights the potential of machine learning to address critical challenges in pest control, fostering more sustainable farming practices.